OSSForks/pytorch
1
0
Fork 0
mirror of https://github.com/zebrajr/pytorch.git synced 2025-12-06 12:20:52 +01:00
Code Issues Actions 38 Packages Projects Releases Wiki Activity

vllm test build (#166146)

Browse Source 
FIx the vllm test build it's broken due to the flashinfer dependency
Pull Request resolved: https://github.com/pytorch/pytorch/pull/166146
Approved by: https://github.com/huydhn
This commit is contained in:
Yang Wang 2025-10-24 19:18:07 +00:00 committed by PyTorch MergeBot
parent 13cda9b89e
commit fdcf402d82
1 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
.github/ci_configs/vllm/Dockerfile vendored
View File

@ -283,6 +283,9 @@ RUN --mount=type=bind,source=${TORCH_WHEELS_PATH},target=/dist \
uv pip install --system $(cat torch_build_versions.txt | xargs) --index-url https://download.pytorch.org/whl/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); \
fi
RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install --system --pre apache-tvm-ffi==0.1.0b15
# Install the vllm wheel from previous stage
RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install --system /wheels/vllm/*.whl --verbose
@ -295,6 +298,8 @@ RUN --mount=type=cache,target=/root/.cache/uv \
ARG torch_cuda_arch_list='8.0;8.9;9.0a;10.0a;12.0'
ENV TORCH_CUDA_ARCH_LIST=${torch_cuda_arch_list}
# TODO(elainewy): remove this once vllm commit is updated, and install flashinfer from pip
# see https://github.com/pytorch/pytorch/pull/165274#issuecomment-3408531784
ARG FLASHINFER_GIT_REPO="https://github.com/flashinfer-ai/flashinfer.git"
ARG FLASHINFER_GIT_REF="v0.2.14.post1"